Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    probability and judgement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    baseHP
    1.18
    ኋ
    1.17
    corollary
    1.15
     '.';
    1.14
     SeekBar
    1.14
    য়াল
    1.12
    रूम
    1.12
    욱
    1.12
    乾隆
    1.12
     Traveler
    1.11
    POSITIVE LOGITS
     blistering
    1.14
    ination
    1.13
    ram
    1.10
    み
    1.09
    判断
    1.07
     judgement
    1.06
     piedi
    1.06
    یه
    1.06
     imposs
    1.05
     disgrace
    1.05
    Act Density 0.001%

    No Known Activations